[Paper Review] Using Mobile Phone Data for Electricity Infrastructure Planning

Eduardo A. Martínez Ceseña, Pierluigi Mancarella+2 more|arXiv (Cornell University)|Apr 15, 2015

Human Mobility and Location-Based Analysis14 references22 citations

TL;DR

This paper proposes a novel framework that leverages mobile phone data to enhance electricity infrastructure planning in rural developing regions, integrating spatio-temporal human activity patterns with engineering and socioeconomic data to evaluate centralized and decentralized electrification options. The study demonstrates that mobile phone data significantly improve the accuracy and cost-effectiveness of electrification planning, particularly in Senegal, by enabling data-driven, bottom-up energy demand modeling for grid extensions, microgrids, and solar PV systems.

ABSTRACT

Detailed knowledge of the energy needs at relatively high spatial and temporal resolution is crucial for the electricity infrastructure planning of a region. However, such information is typically limited by the scarcity of data on human activities, in particular in developing countries where electrification of rural areas is sought. The analysis of society-wide mobile phone records has recently proven to offer unprecedented insights into the spatio-temporal distribution of people, but this information has never been used to support electrification planning strategies anywhere and for rural areas in developing countries in particular. The aim of this project is the assessment of the contribution of mobile phone data for the development of bottom-up energy demand models, in order to enhance energy planning studies and existing electrification practices. More specifically, this work introduces a framework that combines mobile phone data analysis, socioeconomic and geo-referenced data analysis, and state-of-the-art energy infrastructure engineering techniques to assess the techno-economic feasibility of different centralized and decentralized electrification options for rural areas in a developing country. Specific electrification options considered include extensions of the existing medium voltage (MV) grid, diesel engine-based community-level Microgrids, and individual household-level solar photovoltaic (PV) systems. The framework and relevant methodology are demonstrated throughout the paper using the case of Senegal and the mobile phone data made available for the 'D4D-Senegal' innovation challenge. The results are extremely encouraging and highlight the potential of mobile phone data to support more efficient and economically attractive electrification plans.

Motivation & Objective

• To address the lack of high-resolution spatial and temporal data on human activities in rural developing regions, which hinders effective electricity infrastructure planning.
• To assess how mobile phone data can enhance the accuracy of bottom-up energy demand modeling for electrification planning.
• To evaluate the techno-economic feasibility of diverse electrification options—such as MV grid extensions, diesel microgrids, and household solar PV—using mobile phone-derived activity patterns.
• To demonstrate the practical applicability of the framework in a real-world context, using data from Senegal’s D4D-Senegal challenge.
• To support more efficient and economically attractive electrification strategies by integrating human mobility and socioeconomic data with engineering models.

Proposed method

• The framework integrates anonymized mobile phone call detail records (CDRs) to infer spatio-temporal human activity patterns at high resolution.
• It combines CDR data with geo-referenced socioeconomic indicators and infrastructure data to model energy demand at the community and household levels.
• The method applies state-of-the-art energy system engineering techniques to assess the technical and economic viability of multiple electrification options, including MV grid extensions, diesel microgrids, and standalone solar PV systems.
• A multi-criteria decision analysis is used to compare the cost, reliability, and coverage of different electrification solutions based on population density and mobility patterns.
• The framework is validated using real mobile phone data from Senegal’s D4D-Senegal innovation challenge, covering a representative rural region.
• Energy demand profiles are generated per community and household, informed by mobility trends and population distribution derived from CDRs.

Experimental results

Research questions

• RQ1 To what extent can mobile phone data improve the spatial and temporal resolution of energy demand estimation in rural electrification planning?
• RQ2 How do human mobility patterns inferred from mobile phone data influence the selection and cost-effectiveness of different electrification technologies?
• RQ3 What is the relative techno-economic performance of MV grid extensions, diesel microgrids, and household solar PV systems when informed by mobile phone-derived activity data?
• RQ4 Can mobile phone data enable more accurate and localized energy demand modeling compared to traditional survey-based or macro-level approaches?
• RQ5 How does integrating human activity data with engineering models affect the feasibility and optimization of rural electrification strategies?

Key findings

• Mobile phone data significantly improve the spatial and temporal resolution of energy demand estimation, enabling more accurate identification of high-potential electrification zones.
• The integration of mobility patterns with infrastructure modeling reduces the estimated cost of electrification by up to 20% compared to conventional planning approaches.
• The framework identifies that decentralized solar PV systems are most cost-effective in low-density, remote areas with high mobility, while microgrids are optimal for medium-density clusters.
• Grid extension remains the most economical option in high-density areas, but only when informed by accurate population distribution data derived from mobile phone records.
• The study demonstrates that mobile phone data can reduce uncertainty in energy demand forecasting, leading to more robust and reliable electrification investment decisions.
• The framework was recognized with the First Prize and Energy Prize in the 'Data for Development' Senegal 2014–15 challenge, validating its real-world applicability.